Preprint · 2026 · Open access

From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model

Wiktor Kamzela, Jakub Kubiak, Adam Dobosz, Jędrzej Miczke, Anatol Kaczmarek, Piotr Wyrwiński, Wojciech Stefaniak, Wojciech Kotłowski

arXiv (Cornell University) · Published 3 July 2026 · DOI 10.48550/arxiv.2607.03279

Open PDFView at the publisherCite this paper

In brief

“From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model” is a 2026 preprint by Wiktor Kamzela and 7 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
0
References
22
Authors
8

Abstract

Accurate regional weather prediction requires resolving fine-scale structure while remaining consistent with global dynamics. Traditional limited area models rely on computationally expensive simulations, while many learning-based approaches frame the problem as super-resolution, overlooking statistical and physical mismatches across scales. We propose a foundation-model-driven downscaling framework that learns regional refinements of global forecasts by augmenting a pretrained weather model backbone with lightweight, multi-scale prediction heads operating directly in its latent space. Despite being trained on substantially coarser inputs, the pretrained backbone supports regional adaptation at resolutions corresponding to a two-order-of-magnitude increase in grid-cell resolution, without the need for retraining. The proposed approach uses regional numerical simulations as training targets and is evaluated not only against gridded datasets but also against ground-based weather station observations, enabling analysis of systematic biases between global reanalysis, regional simulations, and in-situ weather station observations. Our experiments show improved accuracy in comparison to NWP on most of the metrics at the fraction of computational cost. Moreover, we observe that building on a latent space of globally pre-trained weather foundation model offers better downscaling capabilities than the standard image-based super-resolution approaches.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Kamzela, W., Kubiak, J., Dobosz, A., Miczke, J., Kaczmarek, A., Wyrwiński, P., Stefaniak, W., & Kotłowski, W. (2026). From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.03279

MLA 9

Kamzela, Wiktor, et al. “From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2607.03279.

Chicago

Kamzela, Wiktor, Jakub Kubiak, Adam Dobosz, Jędrzej Miczke, Anatol Kaczmarek, Piotr Wyrwiński, Wojciech Stefaniak, and Wojciech Kotłowski. 2026. “From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.03279.

Harvard

Kamzela, W. et al. (2026) ‘From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model’, arXiv (Cornell University). doi:10.48550/arxiv.2607.03279.

IEEE

W. Kamzela et al., “From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2607.03279.

BibTeX

@misc{kamzela2026from,
  title     = {{From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model}},
  author    = {Kamzela, Wiktor and Kubiak, Jakub and Dobosz, Adam and Miczke, Jędrzej and Kaczmarek, Anatol and Wyrwiński, Piotr and Stefaniak, Wojciech and Kotłowski, Wojciech},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2607.03279},
  url       = {https://doi.org/10.48550/arxiv.2607.03279}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations

  • regional numerical weather prediction
  • super-resolution
  • weather station observations
  • computational efficiency

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Kamzela, W., Kubiak, J., Dobosz, A., Miczke, J., Kaczmarek, A., Wyrwiński, P., Stefaniak, W., & Kotłowski, W. (2026). From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.03279

How many times has this paper been cited?

0 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Wiktor Kamzela, Jakub Kubiak, Adam Dobosz, Jędrzej Miczke, Anatol Kaczmarek, Piotr Wyrwiński, Wojciech Stefaniak, Wojciech Kotłowski.

What is the DOI of this paper?

10.48550/arxiv.2607.03279, permanently at https://doi.org/10.48550/arxiv.2607.03279. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.